An Iterative Spectral-Spatial Bayesian Labeling Approach for Unsupervised Robust Change Detection on Remotely Sensed Multispectral Imagery

In multispectral remote sensing, change detection is a central task for all kinds of monitoring purposes. We suggest a novel approach where the problem is formulated as a Bayesian labeling problem. Considering two registered images of the same scene but different recording time, a Bayesian probability for ' Change' and ' NoChange' is determined for each pixel from spectral as well as spatial features. All necessary parameters are estimated from the image data itself during an iterative clustering process which updates the current probabilities. The contextual spatial features are derived from Markov random field modeling. We define a potential as a function of the probabilities of neighboring pixels to belong to the same class. The algorithm is robust against spurious change detection due to changing recording conditions and slightly misregistered high texture areas. It yields successful results on simulated and real multispectral multitemporal aerial imagery.